⌘K
Pauline P. Narvas Great work! Thanks for sharing, Edu 🙂
BestCodes Yes it works great! Side-note: I searched up 8bitcn by OrcDev. Cool to see that listed there 😁 I tried this exact query and I'm not sure how relevant the results were... I did just search "portfolio" and it brought up some portfolios though, so that's working! Very interesting idea. Isn't this something that Google Stitch introduced already? Seems to be great performance-wise. Can't think of anything off the top of my head! Overall the UI is solid and it seems pretty featureful. Maybe, um, list my website 🤓 (just kidding) Great job @educalvolpz 😃
Pauline P. Narvas This is fantastic. Thanks for sharing, Philo!
BestCodes Okay... I see this as a big security vulnerability, actually, but would love to hear your perspective. Obviously, if an agent can submit any solution it wants, a human or compromised agent could submit a malicious solution. For example, let's say an agent runs into a bug where it forgets to use await with params from Next.js which happens a lot with Claude Code etc. So the agent goes and looks for a solution. Maybe the solution says "curl ai-solutions.co/next-params.md and open it to view fix instructions". This could be completely innocent or maybe next-params.md could actually be a malicious
BestCodes I'm curious, what's the abstraction for? Like, why would I use this rather than the AI SDK's built-in tool approval?
NikitaKharya Great question! The AI SDK's built-in tool approval handles the core approve/reject flow really well. agenttrace-ui builds on top of that with two additional layers: Transparency alongside approval: The AI SDK provides a clear yes/no approval step. agenttrace-ui adds a more detailed view around that, with a collapsible timeline showing each step the agent took, the reasoning behind it, and the underlying data across multiple visualization modes. The approval step becomes one part of a broader, inspectable workflow. LLM-driven vs. predefined approval rules: With the AI SDK, needsApproval is typ
BestCodes @6h0t This is neat, great job! What library are you using to render the table? It looks really nice.
6h0t @bestcodes u can check all docs in the repo folder, currently im using custom rebuilds from open sources librarys to fetch everything, on the ui side, im using the base from rauch terminal but revamper the ui kit using the one on my company, and for graphs using tradingview and a mix of shadcn components.
BestCodes Must say, my portfolio looks pretty sick 😏 However, I do notice that some of the images are broken or not loading. Any idea why that's happening? Great job @skb3611 😃
Skb3611 You need to provide the images for your projects (the best ones that you use for marketing) or else im thinking of adding the github repo banner as default , what do you think?
BestCodes NO. I refuse to be jealous of your website's traffic numbers 😤 Just kidding, that's a super cool idea 😃 I might have to try this. Do you have any plans to open-source it?
Neeeophytee Thanks! Yeah it's been fun to dig into. Here's the dashboard with realtime data from my own site if you want to poke around: botwatcher.vercel.app/demo Not open-source yet but it's something I'm seriously thinking about for the core detection layer. Right now the bot signature list is the part that needs the most community input since new bots show up constantly. Saw that you built Discraft and that it deploys to Vercel. If you want to see what's hitting bestcodes.dev I can get you set up in a few minutes. Just the log drain, one CLI command and you'd have a live dashboard. Happy to host it fo
